Restoration and enhancement on low exposure raw images by joint demosaicing and denoising

Jiaqi Ma, Guoli Wang, Lefei Zhang, Qian Zhang

Abstract: Highlights•We propose a Short2Long raw restoration strategy to process low quality raw images and restore pseudo raw ones for the subsequent subnet. It extracts sufficient information and removes enough noisy points, thus mainly focuses on the denoising task.•We device a Color consistent RGB enhancement mechanism to rearrange raw images and generate the final RGB outputs. With the residual connection and channel-wise attention, it reconstructs the color spatial information and emphasizes more on the demosaicing task.•Both quantitative and qualitative experiments are conducted to demonstrate the superiority of our proposed method. Ablation studies prove the effectiveness of modules. We also illustrate its promising generalization ability on unseen raw data such as images from smartphones.